|
|
Metrics for Optimizing Statistical Machine Translation
Macháček, Matouš ; Bojar, Ondřej (advisor) ; Popel, Martin (referee)
State-of-the-art MT systems use so called log-linear model, which combines several components to predict the probability of the translation of a given sentence. Each component has its weight in the log-linear model. These weights are generally trained to optimize BLEU, but there are many alternative automatic metrics and some of them correlate better with human judgments than BLEU. We explore various metrics (PER, WER, CDER, TER, BLEU and SemPOS) in terms of correlation with human judgments. Metric SemPOS is examined in more detail and we propose some approximations and variants. We use the examined metrics to train Czech to English MT system using MERT method and explore how optimizing toward various automatic evaluation metrics affects the resulting model.
|
|
|
Japanese-Czech Machine Translation
Variš, Dušan ; Bojar, Ondřej (advisor) ; Popel, Martin (referee)
Machine translation (MT) using deep sentence analysis is not as widespread as other MT methods, however we believe that some of its aspects can contribute to the overall translation quality. It is also important to try out deep MT methods with various language pairs. In our case, we experiment with the language pair Japanese-Czech. As a part of this task, we also had to collect and process necessary parallel data. Due to a very small amount of such data being available, we were forced to devise aproaches tackling this problem. Our system is based on the same principles as the TectoMT translation system, therefore it was implemented within the same platform. In the process, we tried to capture at least some basic linguistic phenomena characteristic for Japanese. As a part of our research, we also compared our system with a simple phrase-based baseline. Powered by TCPDF (www.tcpdf.org)
|
|
|
Feature Selection for Factored Phrase-Based Machine Translation
Tamchyna, Aleš ; Bojar, Ondřej (advisor) ; Popel, Martin (referee)
In the presented work we investigate factored models for machine translation. We provide a thorough theoretical description of this machine translation paradigm. We describe a method for evaluating the complexity of factored models and verify its usefulness in practice. We present a software tool for automatic creation of machine translation experiments and search in the space of possible configurations. In the experimental part of the work we verify our analyses and give some insight into the potential of factored systems. We indicate some of the possible directions that lead to improvement in translation quality, however we conclude that it is not possible to explore these options in a fully automatic way.
|
|
|
Measures of Machine Translation Quality
Macháček, Matouš ; Bojar, Ondřej (advisor) ; Kuboň, Vladislav (referee)
Title: Measures of Machine Translation Quality Author: Matouš Macháček Department: Institute of Formal and Applied Linguistics Supervisor: RNDr. Ondřej Bojar, Ph.D. Abstract: We explore both manual and automatic methods of machine trans- lation evaluation. We propose a manual evaluation method in which anno- tators rank only translations of short segments instead of whole sentences. This results in easier and more efficient annotation. We have conducted an annotation experiment and evaluated a set of MT systems using this method. The obtained results are very close to the official WMT14 evaluation results. We also use the collected database of annotations to automatically evalu- ate new, unseen systems and to tune parameters of a statistical machine translation system. The evaluation of unseen systems, however, does not work and we analyze the reasons. To explore the automatic methods, we organized Metrics Shared Task held during the Workshop of Statistical Ma- chine Translation in years 2013 and 2014. We report the results of the last shared task, discuss various metaevaluation methods and analyze some of the participating metrics. Keywords: machine translation, evaluation, automatic metrics, annotation
|
|
|
Automatic Error Correction of Machine Translation Output
Variš, Dušan ; Bojar, Ondřej (advisor) ; Mareček, David (referee)
We present MLFix, an automatic statistical post-editing system, which is a spiritual successor to the rule- based system, Depfix. The aim of this thesis was to investigate the possible approaches to automatic identification of the most common morphological errors produced by the state-of-the-art machine translation systems and to train sufficient statistical models built on the acquired knowledge. We performed both automatic and manual evaluation of the system and compared the results with Depfix. The system was mainly developed on the English-to- Czech machine translation output, however, the aim was to generalize the post-editing process so it can be applied to other language pairs. We modified the original pipeline to post-edit English-German machine translation output and performed additional evaluation of this modification. Powered by TCPDF (www.tcpdf.org)
|
|
|
Converting prose into poetry using neural networks
Gokirmak, Memduh ; Popel, Martin (advisor) ; Dušek, Ondřej (referee)
Title: Converting Prose into Poetry with Neural Networks Author: Memduh Gokirmak Institute: Institute of Formal and Applied Linguistics Supervisor: Martin Popel, Institute of Formal and Applied Linguistics Abstract: We present here our attempts to create a system that generates poetry based on a sequence of text provided to it by a user. We explore the use of machine translation and language model technologies based on the neural network architecture. We use different types of data across three languages in our research, and employ and develop metrics to track the quality of the output of the systems we develop. We find that combining machine translation techniques to generate training data to this end with fine-tuning of pre-trained language models provides the most satisfactory generated poetry. Keywords: poetry machine translation language models iii
|
|
|
Automatic Alignment of Tectogrammatical Trees from Czech-English Parallel Corpus
Mareček, David
Title: Automatic Alignment of Tectogrammatical Trees from Czech-English Parallel Corpus Author: David Mareček Department: Institute of Formal and Applied Linguistics Supervisor: Ing. Zdeněk Žabokrtský, Ph.D. Abstract: The goal of this thesis is to implement and evaluate a software tool for automatic alignment of Czech and English tectogrammatical trees. The task is to find correspondent nodes between two trees that represent an English sentence and its Czech translation. Great amount of aligned trees acquired from parallel corpora can be used for training transfer models for machine translation systems. It is also useful for linguists in studying translation equivalents in two languages. In this thesis there is also described word alignment annotation process. The manual word alignment was necessary for evaluation of the aligner. The results of our experiments show that shifting the alignment task from the word layer to the tectogrammatical layer both (a) increases the interannotator agreement on the task and (b) allows to construct a feature-based algorithm which uses sentence structure and which outperforms the GIZA++ aligner in terms of f-measure on aligned tectogrammatical node pairs. This is probably caused by the fact that tectogrammatical representations of Czech and English sentences are much closer...
|
|
|
Rich Features in Phrase-Based Machine Translation
Kos, Kamil ; Žabokrtský, Zdeněk (referee)
Title: Rich Features in Phrase-Based Machine Translation Author: Kamil Kos Department: Institute of Formal and Applied Linguistics Supervisor: RNDr. Ondřej Bojar, Ph.D. Supervisor's e-mail address: bojar@ufal.mff.cuni.cz Keywords: machine translation, quality evaluation, source-context model, suffix array Abstract: In this thesis we investigate several methods how to improve the quality of statistical machine translation (MT) by using linguistically rich information. First, we describe SemPOS, a metric that uses shallow semantic representation of sentences to evaluate the translation quality. We show that even though this metric has high correlation with human assessment of translation quality it is not directly suitable for system parameter optimization. Second, we extend the log-linear model used in statistical MT by addi- tional source-context model that helps to better distinguish among possible translation options and select the most promising translation for a given context.
|
|
|
Cross-Lingual Information Retrieval in the Medical Domain
Saleh, Shadi ; Pecina, Pavel (advisor) ; Hanbury, Allan (referee) ; Kliegr, Tomáš (referee)
Cross-Lingual Information Retrieval in the Medical Domain Shadi Saleh In recent years, there has been an exponential growth of the digital content available on the Internet, which has correlated with the increasing number of non-English Internet users due to the spread of the Internet across the globe. This raises the importance of unlocking resources for those who want to look up information not limited to the languages they understand. For example, those who want to use the Internet to find medical content related to their health conditions (self-diagnosis) but they do not have access to resources in their language. Cross-Lingual Information Retrieval (CLIR) breaks the lan- guage barriers by allowing search for documents written in a language different from the query language. This thesis tackles the task of CLIR in the medical domain and investigates the two main approaches: query translation (QT) where queries are machine translated to the language of documents and document translation (DT) where documents are translated to the language of queries. We proceed with our research by employing Statistical Machine Translation (SMT) systems that are tuned for the QT approach and the DT approach in the medical domain for seven European languages (Czech, German, French, Spanish, Hungarian, Polish and Swedish) and...
|
|
|
Dolování znalostí z vícejazyčných textových dat
Svozil, Luděk
This paper focuses on the use of machine translation in solving the problems of classification and organization of multilingual text data. Both positive and negative effects of the translation are demonstrated on experiments using real world data. It was confirmed that thanks to the translation the English training set can be used for other languages.
|
guest ::
